Distributed Data Reduction through Agent Collaboration

摘要

Distributed data mining (DDM) is an important research area. One of the approaches suitable for the DDM is to select relevant local patterns from the distributed databases. Such patterns, often called prototypes, are subsequently merged to create a compact representation of the distributed data repositories. In the paper the local prototype selection is carried out independently at each site where instances and features are selected simultaneously by teams of agents. To assure obtaining homogenous prototypes the feature selection requires collaboration of agents. In the paper two agent collaboration strategies producing a common set of features are proposed and experimentally validated. The paper includes a detailed description of the proposed approach and a discussion of the computational experiment results.